© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35877
    Prev
    Next
    INDEX
    Explanations

    gym, casino, sanctuary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    éĴĬ
    -0.10
    ç»Ħ
    -0.10
    stown
    -0.10
    éĿ¢åīį
    -0.09
    åĨĽåĽ¢
    -0.09
    ston
    -0.09
     Grat
    -0.09
    -dominated
    -0.09
    为主çļĦ
    -0.09
    åIJ¯åıij
    -0.09
    POSITIVE LOGITS
    åĨħçļĦ
    0.13
    éĩĮçļĦ
    0.11
    automation
    0.10
    主人
    0.10
    建æĪIJåIJİ
    0.09
    ç¬Ĩ
    0.09
    rio
    0.09
    ALA
    0.09
    .getenv
    0.09
    oran
    0.09
    Activations Density 0.337%

    No Known Activations